Forest Regression Model Research Articles

Machine learning to predict incident atrial fibrillation in patients with acute stroke: FIND-AF STROKE

Abstract Background Atrial fibrillation (AF)-related strokes have a high rate of recurrence, and are associated with substantial morbidity, disability, healthcare expenditure, and mortality.(1-3) Detection of AF promises opportunity to prevent recurrent stroke through conversion of antiplatelet to anticoagulant therapy,(4,5) but use of extended monitoring has cost implications.(6) Thus accurately identifying patients with stroke at high risk for AF is important but previous previous models have been developed in small, unrepresentative cohorts.(7) Purpose To develop and validate a simple novel decision support tool for prediction of incident AF after hospitalisation with stroke through machine learning. Methods We developed the model (FIND-AF STROKE) in UK secondary care and death certificate-linked primary care health record data from individuals aged ≥30 years without known AF hospitalized with a stroke or transient ischaemic attack (Jan 2, 1998 to Feb 28, 2022), randomly divided into training (80%) and testing (20%) datasets. We evaluated logistic regression and random forest models for prediction of 2-year AF risk in the testing dataset with internal bootstrap validation, and compared against the CHA2DS2VASC score. Youden index was used to set a threshold for higher and lower risk. Results Of 35 530 UK individuals (mean age 72.1 (SD 12.7) years, 50.9% women), 1742 (4.8%) had developed incident AF at 2 years. Using feature importance a parsimonious version of the model was created requiring only age, sex, ethnicity (white versus other) and five comorbidities. In the testing dataset prediction performance for the random forest algorithm (area under the receiver operating characteristic (AUROC) 0.710, 95% CI 0.685 – 0.736) was superior to the CHA2DS2VASC score (0.645, 95% CI 0.617-0.672) (Figure 1). The threshold for higher risk using the Youden index was 4.81% which resulted in a negative predictive value of 97.6%, sensitivity 0.712, specificity 0.583. Of the post-stroke patients 44% were labelled at higher risk of AF, who were older, had a higher prevalence of comorbidities, and a 3.3-fold higher incidence of AF post-stroke, than those identified as lower risk (Table 1). Conclusions The machine learning FIND-AF STROKE decision support tool can accurately identify individuals at risk of incident AF after stroke to enable a targeted and cost-effective approach to extended monitoring. Validation within cohorts that have undergone extended monitoring post-stroke will give a more accurate estimation of yield at different risk thresholds.Figure 1

Predicting mortality of type-2 diabetes mellitus by applying machine learning to electronic medical records in the west of scotland and hong kong

Abstract Introduction Type 2 diabetes mellitus (T2DM) is associated with accelerated development of atherosclerosis and a reduced life expectancy. Using machine learning (ML) to identify novel characteristics from electronic medical records (EMRs) associated with prognosis may increase prognostic precision and find new targets for investigation and treatment. Aim We used a novel ML approach to investigate the use of EMRs to predict all-cause mortality in two ethnically and geographically different populations; one from the West of Scotland (WoS) and the other from Hong Kong. Methods We obtained EMRs including demographics, prior comorbidities, laboratory measurements, medications, and mortality. Multivariable Cox regression and time-dependent random forest model were used to identify predictors of all-cause mortality in patients with T2DM. Subsequently, we applied a state-of-the-art ML interpretability method, to gain further insight into the key predictors. Results In WoS, 46,031 individuals received a new diagnosis of T2DM between 2009 and 2019. Their median age was 66 (IQR: 56 to 75) years. Within 10 years, 11,727 (25%) deaths were recorded. In Hong Kong, 273,876 patients with a first-attendance with T2DM at public hospitals or clinics were included, with follow-up until December 2019. The median age of the patients was 64 (IQR: 57 to 72) years. Within 10 years, 91,155 (33%) deaths were recorded. For both cohorts, the strongest predictor for all-cause mortality was prescription of loop diuretics (Figure 1). For the WoS, other important predictors were greater age, lower serum albumin, elevated alanine transaminase (ALT), increased alkaline phosphatase (ALP), and lower estimated glomerular function rate (eGFR) (c-index: 0.83; Brier score: 0.07). For Hong Kong, predictive variables were remarkably similar and included greater age, lower eGFR, lower haemoglobin and lymphocytes, lower serum albumin, and elevated ALP (c-index: 0.85; Brier score: 0.06). Multivariable Cox regression adjusting for age and sex showed a higher mortality amongst those prescribed loop diuretics compared to those who were not (WoS: hazard ratio: 1.549, 95% CI: 1.521 to 1.575; Hong Kong: hazard ratio: 1.745 (95% CI: 1.721 to 1.769). Only a minority of patients prescribed loop diuretics had a diagnosis of heart failure, end-stage renal disease or resistant hypertension. Conclusion Amongst patients with recent-onset T2DM, prescription of loop diuretics was the most important predictor of all-cause mortality in both WoS and Hong Kong. Prescription of loop diuretics might be a pharmacological marker of congestion and undiagnosed heart failure or loop diuretics might have deleterious effects on the outcome of patients with T2DM.Fig 1:Predictors of all-cause Mortality

Diffusion capacity and static hyperinflation as markers of disease progression predict 3-year mortality in COPD: Results from COSYCONET.

Chronic obstructive pulmonary disease (COPD) exhibits diverse patterns of disease progression, due to underlying disease activity. We hypothesized that changes in static hyperinflation or KCO % predicted would reveal subgroups with disease progression unidentified by preestablished markers (FEV1, SGRQ, exacerbation history) and associated with unique baseline biomarker profiles. We explored 18-month measures of disease progression associated with 18-54-month mortality, including changes in hyperinflation parameters and transfer factor, in a large German COPD cohort. Analysing data of 1364 patients from the German observational COSYCONET-cohort, disease progression and improvement patterns were assessed for their impact on mortality via Cox hazard regression models. Association of biomarkers and COPD Assessment test items with phenotypes of disease progression or improvement were evaluated using logistic regression and random forest models. Increased risk of 18-54-month mortality was linked to decrease in KCO % predicted (7.5% increments) and FEV1 (20 mL increments), increase in RV/TLC (2% increments) and SGRQ (≥6 points), and an exacerbation grade of 2 at 18 months. Decrease in KCO % predicted ≥7.5% and an increase of RV/TLC ≥2% were the most frequent measures of 18-month disease progression occurring in ~52% and ~46% of patients, respectively. IL-6 and CRP thresholds exhibited significant associations with medium- and long-term disease measures. In a multicentric cohort of COPD, new markers of current disease activity predicted mid-term mortality and could not be anticipated by baseline biomarkers.

Aboveground Carbon Stock Estimation Based on Backpack LiDAR and UAV Multispectral Imagery at the Forest Sample Plot Scale

Aboveground carbon stocks (AGCs) in forests play an important role in understanding carbon cycle processes. The global forestry sector has been working to find fast and accurate methods to estimate forest AGCs and implement dynamic monitoring. The aim of this study was to explore the effects of backpack LiDAR and UAV multispectral imagery on AGC estimation for two tree species (Larix gmelinii and Betula platyphylla) and to emphasize the accuracy of the models used. We estimated the AGC of Larix gmelinii and B. platyphylla forests using multivariate stepwise linear regression and random forest regression models using backpack LiDAR data and multi-source remote sensing data, respectively, and compared them with measured data. This study revealed that (1) the diameter at breast height (DBH) extracted from backpack LiDAR and vegetation indices (RVI and GNDVI) extracted from UAV multispectral imagery proved to be extremely effective in modeling for estimating AGCs, significantly improving the accuracy of the model. (2) Random forest regression models estimated AGCs with higher precision (Xing’an larch R2 = 0.95, RMSE = 3.99; white birch R2 = 0.96, RMSE = 3.45) than multiple linear regression models (Xing’an larch R2 = 0.92, RMSE = 6.15; white birch R2 = 0.96, RMSE = 3.57). (3) After combining backpack LiDAR and UAV multispectral data, the estimation accuracy of AGCs for both tree species (Xing’an larch R2 = 0.95, white birch R2 = 0.96) improved by 2% compared to using backpack LiDAR alone (Xing’an larch R2 = 0.93, white birch R2 = 0.94).

Developing a suicide risk model for use in the Indian Health Service

We developed and evaluated an electronic health record (EHR)-based model for suicide risk specific to an American Indian patient population. Using EHR data for all patients over 18 with a visit between 1/1/2017 and 10/2/2021, we developed a model for the risk of a suicide attempt or death in the 90 days following a visit. Features included demographics, medications, diagnoses, and scores from relevant screening tools. We compared the predictive performance of logistic regression and random forest models against existing suicide screening, which was augmented to include the history of previous attempts or ideation. During the study, 16,835 patients had 331,588 visits, with 490 attempts and 37 deaths by suicide. The logistic regression and random forest models (area under the ROC (AUROC) 0.83 [0.80–0.86]; both models) performed better than enhanced screening (AUROC 0.64 [0.61–0.67]). These results suggest that an EHR-based suicide risk model can add value to existing practices at Indian Health Service clinics.

Estimation of nighttime PM2.5 concentrations over Seoul using Suomi NPP/VIIRS Day/Night Band

With rapid economic development and urban growth, Seoul experiences severe air pollution due to fine particulate matter with an aerodynamic diameter of ≤2.5 μm (PM2.5), which is detrimental to human health. Although recent studies have extensively focused on estimating daytime PM2.5 concentrations using various types of satellite data, there remains a significant lack of research on nighttime PM2.5 estimations. This study estimated nighttime PM2.5 in Seoul from December 2018 to November 2019 using multiple linear regression (MLR) and random forest (RF) models. These models, which incorporated data on radiance, moon illumination fraction, and terrain height from the Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band (DNB) on board the Suomi National Polar-orbiting Partnership satellite covering all moon phases, also utilized meteorological data from the ERA5 reanalysis by the European Centre for Medium-Range Weather Forecasts (ECMWF). To address multicollinearity, seasonal models were developed using forward stepwise regression and variance inflation factor analysis. DNB radiance analysis indicates that the high intensity of artificial light sources in Seoul significantly reduces the impact of moonlight, leading to notable changes in the DNB radiation associated with PM2.5 concentrations. Consequently, this study estimated nighttime PM2.5 over Seoul across all moon phases. These estimates were then validated through 10-fold cross-validation. The RF model exhibited superior accuracy, with a coefficient of determination (R2) of 0.65–0.90, compared to MLR, with R2 of 0.15–0.50, reflecting seasonal fluctuations in the model performance. The developed models can be applied to estimate reliable nighttime PM2.5 concentrations in megacities with strong artificial light sources, utilizing a comprehensive dataset from satellite observations for all moon phases. Additionally, our findings can serve as scientific data for establishing environmental policies by providing valuable insights into understanding air pollution primarily caused by PM2.5.

Predicting criminal offence in adolescents who exhibit antisocial behaviour: a machine learning study using data from a large randomised controlled trial of multisystemic therapy.

Accurate prediction of short-term offending in young people exhibiting antisocial behaviour could support targeted interventions. Here we develop a set of machine learning (ML) models that predict offending status with good accuracy; furthermore, we show interpretable ML analyses can complement models to inform clinical decision-making. This study included 679 individuals aged 11-17 years who displayed moderate-to-severe antisocial behaviour, from a controlled trial of Multisystemic-therapy in England. The outcome was any criminal offence in the 18 months after study baseline. Four types of ML algorithms were trained: logistic regression, elastic net regression, random forest, and gradient boosting machine (GBM). Prediction models were developed (1) using predictors readily available to clinicians (e.g. sociodemographics, previous convictions), and (2) with additional information (e.g. parenting). Model agnostic feature importance values were calculated and the most important predictors identified. Nested cross-validation with 100 iterations of random data splits and 10-fold cross-validation within each iteration was employed, and the average predictive performance was reported. Among the ML models using readily available predictors, the GBM is the strongest model (AUC 0.85, 95% CI 0.85-0.86); the other models have average AUCs of 0.82. This performance was better than using only the total number of previous offences as the predictor (0.67, 0.66-0.68), and the model simply assuming past offending status as the prediction (0.81, 0.80-0.81). Additional predictors slightly increased the performance of logistic regression and random forest models but decreased the performance of elastic net regression and gradient boosting machine-based models. The potential utility of ML approaches for accurately predicting criminal offences in high-risk youth is demonstrated. Interpretable ML-based predictive models could be utilised in youth services or research to help develop and deliver effective interventions.

Predicting real indoor soundscapes based on auditory and non-auditory factors across different loudness ranges with linear and nonlinear models

Studies on the indoor sound environment have mainly focused on the impact of traffic, neighbor, or ventilation noise on health, annoyance, or sound quality. When conducting such studies in the laboratory, acoustic stimuli are often tailored to the research question, which presumably do not reflect the variation in the acoustic environment at home. Thus, we re-analyzed soundscape data gathered by participants at their homes several times a day. Since the recorded soundscapes differed notably between participants (and their dwellings) in terms of loudness, we investigated if cross-validated linear regression and Random Forest models predicting the soundscape dimensions based on four loudness quartile subsets achieve higher prediction performance compared to models using the full volume range. Our results, which are based on the explanation of the variance in the targets, the correlation between the targets and acoustic and perceptual predictors, and the predictor importance, suggest the use of Random Forest models based on the entire loudness range. In our analysis of predictor importance, Pleasantness was understandably dominated by perceptual measures, whereas Eventfulness was driven through acoustic and psychoacoustic predictors. Interestingly, all models based on quiet soundscapes behaved differently, which provides scope for investigating the underlying causes in future.

Climate and Soil Geochemistry Influence the Soil Organic Carbon Content in Drylands of the Songliao Plain, Northeast China

AbstractThe understanding of the spatial distribution of soil organic carbon (SOC) and its influencing factors is crucial for comprehending the global carbon cycle. However, the impact of soil geochemical and climatic conditions on SOC remains limited, particularly in dryland farming areas. In this study, we aimed to enhance the understanding of the factors influencing the distribution of SOC in the drylands of the Songliao Plain, Northeast China. A dataset comprising 35,188 measured soil samples was used to map the SOC distribution in the region. Multiple linear regression (MLR) and random forest models (RFM) were employed to assess the importance of driving indicators for SOC. We also carried out partial correlation and path analyses to further investigate the relationship between climate and geochemistry. The SOC content in dryland soils of the Songliao Plain ranged from 0.05% to 11.63%, with a mean value of 1.47% ± 0.90%. There was a notable increasing trend in SOC content from the southwest to the northeast regions. The results of MLR and RFM revealed that temperature was the most critical factor, demonstrating a significant negative correlation with SOC content. Additionally, iron oxide was the most important soil geochemical indicator affecting SOC variability. Our research further suggested that climate may exert an indirect influence on SOC concentrations through its effect on geochemical properties of soil. These insights highlight the importance of considering both the direct and indirect impact of climate in predicting the SOC under future climate change.

Research and Empirical Evidence of Machine Learning based Financial Statement Analysis Methods

This study presents a novel approach called FinAnalytix which merging machine learning’s prowess in pattern recognition with financial statement analysis. This integrated algorithm combines deep neural networks and recurrent neural networks for predictive accuracy in stock return analysis, alongside logistic regression and random forest models for robust fraud detection in financial statements. The empirical evidence demonstrates FinAnalytix effectiveness in identifying abnormal financial patterns and predicting market reactions to earnings announcements. The study utilizes extensive data from listed companies, ensuring a comprehensive and practical application. FinAnalytix represents a significant advancement in the field, providing a dual approach to financial analysis for enhancing investment strategies through accurate stock return forecasts and bolstering financial integrity by detecting fraudulent activities. The simulation of the study based on the financial data of 100 sample listed companies. This research not only bridges the gap between traditional financial analysis and modern machine learning techniques but also offers a powerful tool for investors and regulatory bodies in navigating the complex financial landscape.

Modelling personal temperature exposure using household and outdoor temperature and questionnaire data: Implications for epidemiological studies

Non-optimal temperature is a leading risk factor for global disease burden. Most epidemiological studies assessed only outdoor temperature, with important uncertainties on personal exposure misclassification. The CKB-Air study measured personal, household (kitchen and living room), and outdoor temperatures in the summer (MAY-SEP 2017) and winter (NOV 2017-JAN 2018) in 477 participants in China. After data cleaning, ∼88,000 person-hours of data were recorded across each microenvironment. Using multivariable linear regression (MLR) and random forest (RF) models, we identified key predictors and constructed personal temperature exposure prediction models. We used generalised additive mixed effect models to examine the relationships of personal and outdoor temperatures with heart rate. The 24-hour mean (SD) personal and outdoor temperatures were 29.2 (3.8) °C and 27.6 (6.4) °C in summer, and 12.0 (4.0) °C and 7.5 (4.2) °C in winter, respectively. The temperatures across microenvironments were strongly correlated (Spearman’s ρ: 0.86–0.92) in summer. In winter, personal temperature was strongly related to household temperatures (ρ: 0.74–0.79) but poorly related to outdoor temperature (ρ: 0.30). RF algorithm identified household and outdoor temperatures and study date as top predictors of personal temperature exposure for both seasons, and heating-related factors were important in winter. The final MLR and RF models incorporating questionnaire and device data performed satisfactorily in predicting personal exposure in both seasons (R2summer: 0.92; R2winter: 0.68–0.70). We found consistent U-shaped associations between measured and predicted personal temperature exposures and heart rate (lowest at ∼ 14.5 °C), but a weak positive linear association with outdoor temperature. Personal and outdoor temperatures differ substantially winter, but prediction models incorporating household and outdoor temperatures and questionnaire data performed satisfactorily. Exposure misclassification from using outdoor temperature may produce inappropriate epidemiological findings.

Development and Internal Validation of Machine Learning to Predict Postoperative Worse Functional Status after Surgical Treatment for Thoracic Spinal Stenosis.

BACKGROUND The objective of this study was to develop and validate machine learning (ML) algorithms to predict the 30-day and 6-month risk of deteriorating functional status following surgical treatment for thoracic spinal stenosis (TSS). We aimed to provide surgeons with tools to identify patients with TSS who have a higher risk of postoperative functional decline. MATERIAL AND METHODS The records of 327 patients with TSS who completed both follow-up visits were analyzed. Our primary endpoint was the dichotomized change in the perioperative Japanese Orthopedic Association (JOA) score, categorized based on whether it deteriorated or not. The models were developed using Naïve Bays, LightGBM, XGBoost, logistic regression, and random forest classification models. The model performance was assessed by accuracy and the c-statistic. ML algorithms were trained, optimized, and tested. RESULTS The best-performing algorithms for predicting functional decline at 30 days and 6 months after TSS surgery were XGBoost (accuracy=88.17%, c-statistic=0.83) and Naïve Bays (accuracy=86.03%, c-statistic=0.80). Both algorithms presented good calibration and discrimination in our testing data. We identified several significant predictors, including poor quality of intraoperative SSEP/MEP baseline, poor quality of preoperative SSEP, duration of symptoms, operated level, and motor dysfunction of the lower extremity. CONCLUSIONS The best-performing algorithms for predicting functional decline at 30 days and 6 months after TSS surgery were XGBoost (accuracy=88.17%, c-statistic=0.83) and Naïve Bays (accuracy=86.03%, c-statistic=0.80). Both algorithms presented good calibration and discrimination in our testing data. We identified several significant predictors, including poor quality of intraoperative SSEP/MEP baseline, poor quality of preoperative SSEP, duration of symptoms, operated level, and motor dysfunction of the lower extremity.

Sentiment Analysis of Nigerian Opinions Using Logistic Regression and Random Forest Algorithms: A Comparative Study

This study investigates the efficacy of Logistic Regression and Random Forest models in sentiment analysis using Nigerian-based datasets, namely "Gangs of Lagos" and "PeterObi Politics." Sentiment analysis, a vital component of Natural Language Processing (NLP), plays a crucial role in understanding public opinion and sentiment trends, particularly in the context of Nigerian socio-political discourse. Leveraging machine learning techniques, the study examines the performance of these models in predicting sentiment classes, including positive, negative, and neutral sentiments, within the datasets. The findings shed light on the strengths and limitations of Logistic Regression and Random Forest in discerning sentiment nuances prevalent in Nigerian language expressions with Logistic Regression outperforming Random Forest in both cases. This research contributes to the advancement of sentiment analysis methodologies tailored to Nigerian linguistic and cultural contexts, with implications for various applications, including social media monitoring, political analysis, and market research.

Computed tomography radiomics models of tumor differentiation in canine small intestinal tumors.

Radiomics models have been widely exploited in oncology for the investigation of tumor classification, as well as for predicting tumor response to treatment and genomic sequence; however, their performance in veterinary gastrointestinal tumors remains unexplored. Here, we sought to investigate and compare the performance of radiomics models in various settings for differentiating among canine small intestinal adenocarcinoma, lymphoma, and spindle cell sarcoma. Forty-two small intestinal tumors were contoured using four different segmentation methods: pre- or post-contrast, each with or without the inclusion of intraluminal gas. The mesenteric lymph nodes of pre- and post-contrast images were also contoured. The bin settings included bin count and bin width of 16, 32, 64, 128, and 256. Multinomial logistic regression, random forest, and support vector machine models were used to construct radiomics models. Using features from both primary tumors and lymph nodes showed significantly better performance than modeling using only the radiomics features of primary tumors, which indicated that the inclusion of mesenteric lymph nodes aids model performance. The support vector machine model exhibited significantly superior performance compared with the multinomial logistic regression and random forest models. Combining radiologic findings with radiomics features improved performance compared to using only radiomics features, highlighting the importance of radiologic findings in model building. A support vector machine model consisting of radiologic findings, primary tumors, and lymph node radiomics features with bin count 16 in post-contrast images with the exclusion of intraluminal gas showed the best performance among the various models tested. In conclusion, this study suggests that mesenteric lymph node segmentation and radiological findings should be integrated to build a potent radiomics model capable of differentiating among small intestinal tumors.

Development and Validation of an Algorithm to Predict Stillbirth Gestational Age in Medicaid Billing Records

Abstract Introduction With Medicaid covering half of US pregnancies, Medicaid Analytic eXtract (MAX) provides a valuable data source to enrich understanding about stillbirth etiologies. Objective We developed and validated a claims-based algorithm to predict GA at stillbirth. Method We linked the stillbirths identified in MAX 1999-2013 to Florida Fetal Death Records (FDRs) to obtain clinical estimates of GA (N=825). We tested several algorithms including using a fixed median GA, median GA at the time of specific prenatal screening tests, and expanded versions considering additional predictors of stillbirth within including linear regression and random forest models. We estimated the proportion of pregnancies with differences of ± 1, 2, 3 and 4 weeks between the predicted and FDR GA and the model mean square error (MSE). We validated the selected algorithms in two external samples. Results The best performing algorithm was a random forest model (MSE of 12.67 weeks2) with 84% of GAs within ± 4 weeks. Assigning a fixed GA of 28 weeks resulted in an MSE of 60.21 weeks2 and proportions of GA within ± 4 weeks of 32%. We observed consistent results in the external samples. Discussion Our prediction algorithm for stillbirths can facilitate pregnancy research in the Medicaid population.

Machine learning-enabled attapulgite/polyimide nanofiber composite aerogels-based colorimetric sensor array for real-time monitoring of balsa fish freshness

This paper presents the development and application of attapulgite/polyimide nanofiber composite aerogels (ATP/PI NFAs) integrated with a range of acid-base indicators, fabricated using electrospinning and freeze-drying technologies. A detailed characterization of the ATP/PI NFAs revealed a 3D multi-level pore structure that enhanced the mass transfer of target gas molecules and their interaction with probe molecules. Utilizing machine learning approaches, we designed an ATP/PI NFAs-based colorimetric sensor array capable of real-time evaluation of balsa fish freshness. Color features sensitive to changes in freshness were selected using principal component analysis and random forest. Partial least squares regression and random forest regression models were established, achieving the prediction of total volatile basic nitrogen content in balsa fish. The system was validated using a national standard method to demonstrate its accuracy and practicality. The combination of advanced ATP/PI NFAs-based colorimetric sensor array with robust machine learning models paves the way for food safety monitoring.

Construction of an interpretable model for predicting survival outcomes in patients with middle to advanced hepatocellular carcinoma (≥5cm) using lasso-cox regression.

In this retrospective study, we aimed to identify key risk factors and establish an interpretable model for HCC with a diameter ≥ 5cm using Lasso regression for effective risk stratification and clinical decision-making. In this study, 843 patients with advanced hepatocellular carcinoma (HCC) and tumor diameter ≥ 5cm were included. Using Lasso regression to screen multiple characteristic variables, cox proportional hazard regression and random survival forest models (RSF) were established. By comparing the area under the curve (AUC), the optimal model was selected. The model was visualized, and the order of interpretable importance was determined. Finally, risk stratification was established to identify patients at high risk. Lasso regression identified 8 factors as characteristic risk factors. Subsequent analysis revealed that the lasso-cox model had AUC values of 0.773, 0.758, and 0.799, while the lasso-RSF model had AUC values of 0.734, 0.695, and 0.741, respectively. Based on these results, the lasso-cox model was chosen as the superior model. Interpretability assessments using SHAP values indicated that the most significant characteristic risk factors, in descending order of importance, were tumor number, BCLC stage, alkaline phosphatase (ALP), ascites, albumin (ALB), and aspartate aminotransferase (AST). Additionally, through risk score stratification and subgroup analysis, it was observed that the median OS of the low-risk group was significantly better than that of the middle- and high-risk groups. We have developed an interpretable predictive model for middle and late HCC with tumor diameter ≥ 5cm using lasso-cox regression analysis. This model demonstrates excellent prediction performance and can be utilized for risk stratification.

Geospatial modelling of ambient air pollutants and chronic obstructive pulmonary diseases at regional scale in Pakistan.

Pakistan is among the South Asian countries mostly vulnerable to the negative health impacts of air pollution. In this context, the study aimed to analyze the spatiotemporal patterns of chronic obstructive pulmonary disease (COPD) incidence and its relationship with air pollutants including aerosol absorbing index (AAI), carbon monoxide, sulfur dioxide (SO2), and nitrogen dioxide. Spatial scan statistics were employed to identify temporal, spatial, and spatiotemporal clusters of COPD. Generalized linear regression (GLR) and random forest (RF) models were utilized to evaluate the linear and non-linear relationships between COPD and air pollutants for the years 2019 and 2020. The findings revealed three spatial clusters of COPD in the eastern and central regions, with a high-risk spatiotemporal cluster in the east. The GLR identified a weak linear relationship between the COPD and air pollutants with R2 = 0.1 and weak autocorrelation with Moran's index = -0.09. The spatial outcome of RF model provided more accurate COPD predictions with improved R2 of 0.8 and 0.9 in the respective years and a very low Moran's I = -0.02 showing a random residual distribution. The RF findings also suggested AAI and SO2 to be the most contributing predictors for the year 2019 and 2020. Hence, the strong association of COPD clusters with some air pollutants highlight the urgency of comprehensive measures to combat air pollution in the region to avoid future health risks.

Discovery and validation of colorectal cancer tissue-specific methylation markers: a dual-center retrospective cohort study

Background and purposeEarly detection, diagnosis, and treatment of colorectal cancer and its precancerous lesions can significantly improve patients’ survival rates. The purpose of this research is to identify methylation markers specific to colorectal cancer tissues and validate their diagnostic capability in colorectal cancer and precancerous changes by measuring the level of DNA methylation in stool samples.MethodWe analyzed samples from six cancer tissues and adjacent normal tissues and fecal samples from 758 participants, including 62 patients with interfering diseases. Bioinformatics databases were used to screen for candidate biomarkers for CRC, and quantitative methylation-specific PCR methods were applied for identification. The methylation levels of the candidate biomarkers in fecal and tissue samples were measured. Logistic regression and random forest models were built and validated using fecal sample data from one of the centers, and the independent or combined diagnostic value of the candidate biomarkers in fecal samples for CRC and precancerous lesions was analyzed. Finally, the diagnostic capability and stability of the model were validated at another medical center.ResultsThis study identified two colorectal cancer CpG sites with tissue specificity. These two biomarkers have certain diagnostic power when used individually, but their diagnostic value for colorectal cancer and colorectal adenoma is more significant when they are used in combination.ConclusionThe results indicate that a DNA methylation biomarker combined diagnostic model based on two CpG sites, cg13096260 and cg12587766, has the potential for screening and diagnosing precancerous lesions and colorectal cancer. Additionally, compared to traditional diagnostic models, machine learning algorithms perform better but may yield more false-positive results, necessitating further investigation.

Gender-specific microbial signatures in saliva: Unveiling the association between the oral microbiome and the pathogenesis of glioma

The intricate interplay between the human oral microbiome and systemic health is increasingly being recognized, particularly in the context of central nervous system pathologies such as glioblastoma. In this study, we aimed to elucidate gender-specific differences in the salivary microbiome of glioma patients by utilizing 16S rRNA sequencing data from publicly available salivary microbiome datasets. We conducted comprehensive bioinformatics analysis, encompassing quality control, noise reduction, species classification, and microbial community composition analysis at various taxonomic levels. Machine learning algorithms were employed to identify microbial signatures associated with glioma. When compared to healthy controls, our analysis revealed distinct differences in the salivary microbiota of glioma patients. Notably, the genera Leptotrichia and Atopobium exhibited significant variations in abundance between genders. Leptotrichia was prevalent in healthy females but exhibited a reduced abundance in female glioma patients. In contrast, Atopobium was more abundant in male glioma patients. These findings suggest that hormonal influences might play a role in shaping the salivary microbiome and its association with glioma. We utilized a combination of LASSO-logistic regression and random forest models for feature selection, and identified key microbial features that differentiated glioma patients from healthy controls. We developed a diagnostic model with high predictive accuracy and area under the curve and principal component analysis metrics confirmed its robustness. The analysis of microbial markers, including Atopobium and Leptotrichia, highlighted the potential of the salivary microbiota as a non-invasive biomarker for the diagnosis and prognosis of glioma. Our findings highlight significant gender-specific disparities in the salivary microbiome of patients with glioma, offering new insights into the pathogenesis of glioma and paving the way for innovative diagnostic and therapeutic strategies. The use of saliva as a diagnostic fluid, given its ease of collection and non-invasive nature, holds immense promise for monitoring systemic health and the trajectory of disease. Future research should focus on investigating the underlying mechanisms by which the salivary microbiome influences the development of glioma and identifying potential microbiome-targeted therapies to enhance the management of glioma.